Implicit Feedback for User-Adaptive Systems by Analyzing the Users’ Speech

This paper describes an approach to recognize the gender and age of a user on the basis of her/his speech. Within a two-level framework, machine learning techniques are applied to learn several appropriate classifiers whose results are combined on the top level to improve the overall classification of the user. As a part of the user model, the information about the user’s age and gender can be an important basis for appropriate adaptation decisions.